← Guides

Langfuse vs LangSmith vs Opik (and others): how to debug AI agents

By Jacob Holm · October 20, 2026

Agents rarely crash. More often they "finish" with the wrong answer: they call the same tool three times, keep going after a 404, or make up a value and report success. Logs of the final output won't show you that. You need a trace of every step (each model call, tool call, and sub-agent, with its inputs, outputs, tokens, cost, and latency) and evals that check the results.

What to look for

Langfuse: open source, with every feature on the free plan

Langfuse is open source and free to self-host. It offers agent traces and graphs, session and user tracking, token and cost tracking, OpenTelemetry ingestion, datasets, LLM-as-judge evaluators, and human annotation. The cloud Hobby plan is free, with 50k units a month and 30 days of data access. Core is $29/mo (100k units, then $8 per 100k), and Pro is $199/mo. A unit is any trace, observation, or score you send.

LangSmith: tracing and evals from the LangChain team

LangSmith handles tracing and evals for any framework, not only LangChain. The Developer plan is free for 1 seat with 5k base traces a month. Plus is $39/seat/mo with 10k base traces, then pay as you go. Base traces are kept for 14 days, and extended traces are kept for 180 days. LangSmith also sells Engine, which monitors traces, groups failures into issues, and proposes fixes along with evals. It's billed per run in LSUs (1 LSU = $1), and LangChain estimates about 7 to 45 LSUs a run.

Opik: open source from Comet, with test suites

Opik is open source, and Comet says the self-hosted version has the full feature set. It includes agent tracing, execution graphs, sessions, cost tracking, error surfacing, OpenTelemetry support, pass/fail test suites with assertions, and more than 30 built-in eval metrics. Free Cloud includes 25k spans a month with 60-day retention. Pro Cloud is $19/mo for 100k spans, then $5 per 100k.

Others worth a look

OpenTelemetry export: keep your options open

Langfuse, Opik, and Phoenix all accept OpenTelemetry traces. If you build on Claude, the Claude Platform can now send OpenTelemetry traces (public beta, announced Oct 14, 2026) for Messages API requests, Managed Agents turns, model calls, and server tools to any OTLP/HTTP endpoint. An org admin sets this up as a destination in the Claude Console, and no code changes are needed. You choose whether it sends only metadata or full content. The Claude SDKs can also emit client-side spans.

How to catch silent failures

Which one to pick

See every option in Observability for AI agents.

Options at a glance

ToolWhat it doesPricingLicense
LangfuseOpen-source LLM observability and evalsFree tier; paid from $29/moOpen source
LangSmithTracing and evals for LLM appsFree dev seat; Plus $39/seat/mo + usageProprietary
OpikOpen-source tracing and evals for LLM apps and agents (by Comet)Free (OSS self-host or free cloud); Pro $19/moOpen source
LaminarOpen-source agent observability: traces LLM calls, tool calls and sub-agents, and Signals cluster agent failures you didn't define in advanceFree tier; usage-based paid plansOpen source
ArizeAI observability; Phoenix is OSSFree tier; Pro $50/moPartly open source
HeliconeLLM observability and gatewayFree tier; paid from $79/moOpen source
BraintrustEvals and observability for AI productsFree tier; paid plansProprietary

We list what each vendor's own site says. Pricing changes often, so check it on the vendor's site before you commit.

Liked this guide? Get one new agent-infra guide a week.

One short email with a new guide and the tools worth knowing about. Free, and you can unsubscribe anytime.